Dear all,
my concern is to estimate a panel with the Hausman Taylor methodology. This estimator assumes some of the time-invariant and time-variant covariates to be endogenous.
I would like to test the endogeneity of some regressors, i.e. correlation with individual random effect (remember that a two-component error process it is usually assumed, where I label the 'individual random effect' what is the time-invariant component). I heard from a test proposed by Baltagi, Bresson and Pirotte (2003): "Fixed Effects, Random Effects or Hausman-Taylor? A Pretest Estimator", published in Economics Letters 79, pp. 361-369. (this test is based on the well-known Hausman Specification test). Is this test implemented in Stata?
Are there other ways to test the endogeneity of regressors and by this to analyze whether Hausman-Taylor might be more appropriate than Random Effects?
Best,
John.
--
John Bunge
Debt and Finance Analysis Unit
United Nations Conference on Trade and Development (UNCTAD)
Palais des Nations
1211 Genève 10
Switzerland
Office: +41 229175902
Mobile: +41 762901769
_____________________________________________________________________
Der WEB.DE SmartSurfer hilft bis zu 70% Ihrer Onlinekosten zu sparen!
http://smartsurfer.web.de/?mc=100071&distributionid=000000000066
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
